Retrieve cosmetic ingredient safety data for regulatory compliance and safety assessment. Input: common name, INCI name, or CAS number (e.g. 'retinol', 'RETINOL', '68-26-8'). Returns: NOAEL study values with species/route/duration, pre-calculated Margin of Safety from SCCS opinions, GHS hazard cl...
Risk signalsAccepts freeform code/query input (query)
Part of the Cosmetic Regulatory server.
Free to start. No card required.
AI agents call check_ingredient to retrieve information from Cosmetic Regulatory without modifying any data. This is common in research, monitoring, and reporting workflows where the agent needs context before taking action. Because read operations don't change state, they are generally safe to allow without restrictions -- but you may still want rate limits to control API costs.
Even though check_ingredient only reads data, uncontrolled read access can leak sensitive information or rack up API costs. An agent caught in a retry loop could make thousands of calls per minute. A rate limit gives you a safety net without blocking legitimate use.
Read-only tools are safe to allow by default. No rate limit needed unless you want to control costs.
{
"version": "1",
"default": "deny",
"tools": {
"check_ingredient": {}
}
}See the full Cosmetic Regulatory policy for all 4 tools.
These attack patterns abuse exactly the kind of access check_ingredient gives an agent. Each links to the full case and the policy that stops it:
Other read tools across the catalogue. The same approach applies to each: allow, with a rate cap to control cost.
Retrieve cosmetic ingredient safety data for regulatory compliance and safety assessment. Input: common name, INCI name, or CAS number (e.g. 'retinol', 'RETINOL', '68-26-8'). Returns: NOAEL study values with species/route/duration, pre-calculated Margin of Safety from SCCS opinions, GHS hazard classifications, EU/US/Korea/Japan/ASEAN/Saudi/Canada/Australia regulatory status across 12 jurisdictions, SCCS opinion summaries, CIR safety conclusions, dermal absorption profiles, sensitization data with patch-test frequencies, endocrine disruption flags, SVHC status, IFRA fragrance restrictions, China IECIC listing, and EU allergen classifications. Sources include ECHA IUCLID dossiers, SCCS opinions, CIR safety assessments, FDA, ToxValDB, and EPA CompTox. Database: 30,553 cosmetic ingredients, 174,973 NOAEL studies, 8,898 sensitization assays, 5,267 CIR safety conclusions, and 1,583 SCCS opinions. Use for cosmetic ingredient safety assessment. Do not use for full formula scans (use check_formula), MoS calculations with custom concentration (use calculate_mos), food additive questions, or pharmaceutical actives.. It is categorised as a Read tool in the Cosmetic Regulatory MCP Server, which means it retrieves data without modifying state.
Register the Cosmetic Regulatory MCP server in PolicyLayer and add a rule for check_ingredient: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Cosmetic Regulatory. Nothing to install.
check_ingredient is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the check_ingredient rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for check_ingredient. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
check_ingredient is provided by the Cosmetic Regulatory MCP server (https://roots-mcp-server.rootsbybenda.workers.dev/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 4 Cosmetic Regulatory tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
4,600+ MCP servers and 31,000+ tools scanned and risk-classified.